Application of Perceptron Networks in Recommending Medical Diagnosis

Abstract

Artificial intelligence applications in medicine is the major and evolutionary topic in the technology world. Neural networks is an important branch of machine learning which is inspired from biological neural networks. Neural networks are useful in making proper decisions in rational environments with uncertainty. The neural networks perform better computation with high power with the help of the multiple interconnected neurons which act as processing elements. Decision theory along with probabilistic theory gives the good way to make the right decisions. Neural Network systems help in linking the health observations with the health knowledge database to take better decisions for good health. The ability of a neural network to learn by example can be implemented for taking decisions that would increase the rate of providing the better medical care facilities. This paper presents a novel methodology to implement supervised learning networks that is perceptron networks in medical diagnosis for providing such good decisions to the doctors in helping patients by also providing a good health care.

Acceptance of clinical decision support systems in Saudi healthcare organisations

“…Other challenges of implementing CDSS in rural healthcare in developing countries included electricity outages and inadequate technical knowledge (Zakane et al, 2014). The obstacles associated to CDSS itself include the large number of alerts, the high cost of combining the system with existing health care practice settings, and the potential negative effects on privacy, confidentiality, data accuracy, and alert generation (Gullapalli, Brungi, and Gopichand, 2015). Khalifa (2016) thus categorised the challenges facing the adoption of HIS in Saudi Arabi as: financial challenges, organizational challenges, and regulatory challenges.…”

Untitled

“…The most commonly cited barriers to implementing a DSS were a lack of CDSS understanding among physicians, a large number of superfluous warnings in the system, the requirement for technical help, and the time spent using CDSS being deducted from time spent communicating with patient's electricity outages and a lack of technical understanding were also hurdles in deploying CDSS in rural health care in poor countries (Zakane et al, 2014). [12,13] The enormous number of alerts, the high expense of integrating the system with existing health-care practice settings, and the potential negative consequences on privacy, confidentiality, data accuracy, and alert creation are all barriers connected with CDSS (Gullapalli et al, 2015). [14] Furthermore, the previous study by Khalifa in 2016 allocated the barriers related to CDSS in Saudi Arabia into three categories; financial, organizational, and regulatory.…”

“…[12,13] The enormous number of alerts, the high expense of integrating the system with existing health-care practice settings, and the potential negative consequences on privacy, confidentiality, data accuracy, and alert creation are all barriers connected with CDSS (Gullapalli et al, 2015). [14] Furthermore, the previous study by Khalifa in 2016 allocated the barriers related to CDSS in Saudi Arabia into three categories; financial, organizational, and regulatory. [15] However, in rural health-care settings, most cited challenges of implementing CDSS included electricity outages and inadequate technical knowledge.…”